PREFIX : <https://raw.githubusercontent.com/arvados/bh20-seq-resource/master/bh20sequploader/bh20seq-shex.rdf#>
PREFIX MainSchema: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
PREFIX hostSchema: <http://biohackathon.org/bh20-seq-schema#hostSchema/>
PREFIX cc:  <https://creativecommons.org/ns#>
PREFIX cclicenses:  <https://creativecommons.org/licenses/>
PREFIX dc:  <http://purl.org/metadata/dublin_core_elements#>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX obo: <http://purl.obolibrary.org/obo/>
PREFIX sio: <http://semanticscience.org/resource/>
PREFIX efo: <http://www.ebi.ac.uk/efo/>
PREFIX evs: <http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#>
PREFIX edam: <http://edamontology.org/>
PREFIX wikidata: <http://www.wikidata.org/entity/>

:submissionShape CLOSED {
  MainSchema:host   @:hostShape ;
  MainSchema:sample @:sampleShape ;
  MainSchema:submitter @:submitterShape ;
  MainSchema:technology @:technologyShape ;
  MainSchema:virus @:virusShape;
  MainSchema:license @:licenseShape ?;
}

## documentation: #(name of option in yaml), ontology label, mandatory|optional, type
## entries marked with ?????? need review

:hostShape  CLOSED {
    efo:EFO_0000532 [ obo:NCBITaxon_~ ] ;   #(host_species host), mandatory field, from namespace obo:NCBITaxon
    sio:SIO_000115 xsd:string ?;            #(host_id), identifier, optional string
    obo:PATO_0000047 [ obo:PATO_0000384 obo:PATO_0000383 obo:PATO_0001340] ?;   #(host_sex) biological sex, optional, one selected value
    obo:PATO_0000011 xsd:integer ?;         #(host_age) age, optional integer
    obo:NCIT_C42574 [ obo:UO_~ ] ?;         #host_age_unit, optional from namespace obo:UO
	obo:NCIT_C25688 [obo:NCIT_C115935 obo:NCIT_C3833 obo:NCIT_C25269 obo:GENEPIO_0002020 obo:GENEPIO_0001849 obo:NCIT_C28554 obo:NCIT_C37987 ] ? ; #(host_health_status) status, optional, one selected value
    efo:EFO_0000727 xsd:string ?;           #(host_treatment), treatment, optional
    obo:VO_0000002 xsd:string {0,10};       #(host_vaccination), vaccination, optional list of String 0-10
    sio:SIO_001014 [ obo:HANCESTRO_~ ] ? ;  #(ethnicity), ethnicity from obo:HANCESTRO
    sio:SIO_001167 xsd:string ?;            #(additional_host_information), comment, optional, string
}

:sampleShape CLOSED {
    sio:SIO_000115 xsd:string;          #(sampleId), identifier, mandatory string
    evs:C25164 xsd:string;              #(collection_date), date, mandatory, string but should be date
    obo:GAZ_00000448 [wikidata:~] ;     #(collection_location), geographic location, mandatory, from wikidata namespace
    obo:OBI_0001895 xsd:string ?;       #(collector_name), specimen collector, optional string
    obo:NCIT_C41206 xsd:string ?;       #(collecting_institution) Institute, optional string
    obo:OBI_0001479 [ obo:NCIT_~ ] {0,2} ;  #(specimen_source), specimen from organism, optional, from obo:NCIT
    obo:OBI_0001472 xsd:string ?;       #(sample_storage_conditions), specimen with known storage state, optional string
    sio:SIO_001167 xsd:string ?;        #(additional_collection_information), comment, optional, string
    edam:data_2091 IRI {0,3};           #(source_database_accession), Accession, optional, IRI 0-3
}

:submitterShape CLOSED {
    obo:NCIT_C42781 xsd:string + ;      #(authors), Author, mandatory, list 1-*
    sio:SIO_000116 xsd:string *;        #(submitter_name), name, optional 0-*
    sio:SIO_000172 xsd:string ?;        #(submitter_address), address, optional, string
    obo:NCIT_C37984 xsd:string ?;       #(originating_lab) Laboratory, optional, string
    obo:NCIT_C25407  xsd:string ?;      #(lab address), Address, optional, string
    obo:NCIT_C37900 xsd:string ?;       #(provider), Provider, optional, string
    obo:NCIT_C164332 xsd:string ?;       #(submitter_sample_id), Sample identifier, optional, string
    obo:NCIT_C19026 xsd:string ?;       #(publication), Scientific Publication, optional string
    obo:APOLLO_SV_00000496 /https:\u002F\u002Forcid.org\u002F.{4}-.{4}-.{4}-.{4}/ {0,10};   #(submitter_orcid) identifier, optional but given regular expression
    sio:SIO_001167 xsd:string ?;        #(additional_submitter_information), comment, optional string
}

:technologyShape CLOSED {
    obo:NCIT_C153598 IRI {1,3} ;         #(sample_sequencing_technology), DNA Sequencing, mandatory
    obo:GENEPIO_0000090 [obo:GENEPIO_0001628 obo:GENEPIO_0002028 ] ;    #(assembly method), assembly method, mandatory, one of the two
    efo:EFO_0004917 xsd:string ?;        #(alignment_protocol), high throughput sequence alignment protocol, optional
    obo:FLU_0000848 xsd:double OR xsd:integer {0,3};    #(sequence coverage) sequence coverage, optional
    sio:SIO_001167 xsd:string ?;        #(additional_technology_information), comment, optional, string
}

:virusShape CLOSED {
    edam:data_1875 [ obo:NCBITaxon_~ ] ;    # (virus_species) NCBI taxon, mandatory, from namespace obo:NCBITaxon_
    sio:SIO_010055 xsd:string ?;            # (virus_strain) strain, optional string
}

:licenseShape CLOSED {
    cc:License [ cclicenses:~ ] ;
    dc:Title xsd:string ?;
    cc:attributionName xsd:string ?;
    cc:attributionURL /^http/ ;
    cc:attributionSource xsd:string ?;
}